© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2956
    Prev
    Next
    INDEX
    Explanations

    be + adjective or being + adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    เป็น
    0.44
     isValid
    0.40
    을
    0.38
     caches
    0.38
    (`
    0.38
     最
    0.37
    を使用
    0.36
    是一种
    0.36
    }-
    0.36
     patches
    0.35
    POSITIVE LOGITS
     capazes
    0.57
     able
    0.53
     aware
    0.49
     قادر
    0.47
     tempted
    0.47
     unable
    0.46
     capaces
    0.46
     willing
    0.46
     atentos
    0.44
     wary
    0.43
    Activations Density 0.191%

    No Known Activations